aboutsummaryrefslogtreecommitdiffstats
path: root/camel/camel-charset-map.c
diff options
context:
space:
mode:
authorNot Zed <NotZed@HelixCode.com>2000-11-07 20:31:10 +0800
committerMichael Zucci <zucchi@src.gnome.org>2000-11-07 20:31:10 +0800
commitc70c4c35f3788bb210b6f01205e0bc71b4414c4f (patch)
tree4357ace78279168e32024a4311fca6d91b123678 /camel/camel-charset-map.c
parent9acf78e29dab60c2acb2312fffe42020a00df59c (diff)
downloadgsoc2013-evolution-c70c4c35f3788bb210b6f01205e0bc71b4414c4f.tar.gz
gsoc2013-evolution-c70c4c35f3788bb210b6f01205e0bc71b4414c4f.tar.zst
gsoc2013-evolution-c70c4c35f3788bb210b6f01205e0bc71b4414c4f.zip
Implement a complete() function, now we need one. (filter): Upgraded to
2000-11-07 Not Zed <NotZed@HelixCode.com> * camel-mime-filter-bestenc.c (complete): Implement a complete() function, now we need one. (filter): Upgraded to match rfrc2045 properly. Checks also for length of line and valid CRLF sequences. (camel_mime_filter_bestenc_get_best_encoding): Do the work of working out what is the best encoding given what we found about the stream. * camel-mime-part.c (camel_mime_part_encoding_to_string): Use a lookup table to get the encoding naem, and add the binary type. (camel_mime_part_encoding_from_string): Likewise for the reverse. * camel-mime-part.h: Added the binary encoding type, see rfc2045. * camel-mime-utils.c (header_param_list_format_append): Dont put a space before ;'s in parameter lists, makes them more readable/consistent. * camel-mime-message.c (multipart_has_8bit_parts): Cleaned up the old stuff, well removed it. (camel_mime_message_set_best_encoding): Added another argument that lets you select what you want to set the best of. i.e. for smtp transport we only need 7 bit, and dont need to optimise the charset (although of course, we should always). (find_best_encoding): Implement this feature, if we are not getting the best charset, use the one we have. (best_encoding): Set the charset on the part appropriately. Sigh, the interfaces for this are nonexistant. (find_best_encoding): Tell the bestenc filter that lf should be treated as crlf for the purposes of determining encodings. 2000-11-06 Not Zed <NotZed@HelixCode.com> * camel-charset-map.c (camel_charset_init): Init function for an iterative charset determinator. (camel_charset_step): Iterate another buffer. (camel_charset_mask): Removed, since it couldn't have worked. (camel_charset_best): Use the iterative interface to do the work. (camel_charset_best_name): Get the best name for a charset so far. * camel-mime-filter-bestenc.c: New class, a stream filter that can be used to memory-efficiently determine the best encoding and/or charset to use for a given stream of bytes. * Makefile.am (libcamelinclude_HEADERS): Added stream-null*. (libcamel_la_SOURCES): Added bestenc* * camel-stream-null.c: New class, a null-stream, that always succeeds, and never has any contents. * camel-stream.c: Minor pointless changes. Was going to do something else but changed my mind. Added trivial default implementations for all callbacks. * camel-mime-message.h: Cleaned up some old cruft. * camel-folder-summary.c (camel_folder_summary_format_address): address_list_format() no longer encodes, so we dont need to decode it. * camel-address.c (camel_address_unformat): New function, attempts to reverse the formatting process on display addresses. (camel_address_length): New function to get the number of addresses, without having to peek the structure. * camel-mime-message.c (camel_mime_message_set_from): Fix a typo. (camel_mime_message_finalize): Only unref from/reply_to if we have it. (camel_mime_message_set_recipients): New function - set the recipients as a CamelInternetAddress. This function effectively deprecates the older recipient setting functions. (camel_mime_message_add_recipient): What the hell, i'll bite the bullet. Terminate this function. The old api was ambiguious and inefficient and didn't work right anyway. (camel_mime_message_remove_recipient_address): And this one. (camel_mime_message_remove_recipient_name): And this one too. (camel_mime_message_set_recipients): If we set an empty header, then remove it from the header list. Allow a null receipient object to clear a header. (camel_mime_message_set_from): Likewise, if setting an empty from address. (camel_mime_message_encode_8bit_parts): Eeek!! camel_stream_mem_new_with_byte_array owns the byte_array we give it, so make sure we dont free any of it! (camel_mime_message_encode_8bit_parts): Infact, i'll just rewrite the whole lot, its a bit of a mess. Should really rename it and make it a little more useful too, lets see ... (best_encoding): This has a string interface? Oh boy. (camel_mime_message_foreach_part): New experimental function to iterate over all message parts. Might not remain. (camel_mime_message_has_8bit_parts): New implementation using foreach_part. Fixed a couple of problems. (find_best_encoding): New function, that finds the best encoding for a given part (will probably be moved to camel-mime-part), and also the best charset to use if it is a text part. Since one affects the other it is a two pass process, but uses streams and not memory to achieve this. (camel_mime_message_set_best_encoding): Uses the function above to configure an entire message for the best encoding possible given transport constraints. (camel_mime_message_encode_8bit_parts): Reimplemented to use the function above to perform the work. * camel-internet-address.c (camel_internet_address_format_address): Dont put <> around a lone address with no real name. (camel_internet_address_encode_address): Similarly. (internet_decode): Actually return the count of decoded addresses. (internet_unformat): Implement the unformatting routine. 2000-11-05 Not Zed <NotZed@HelixCode.com> * providers/smtp/camel-smtp-transport.c (_send_to): Changed to get the internetaddress directly, rather than having to parse it itself. * camel-address.c (camel_address_format): Added a new function which will format address, suitable for display. (camel_address_cat): Concatentate 1 camel address onto another. It is upto the caller to ensure the addresses are of compatible types. (camel_address_new_clone): New function to create a new address by copying an existing one of the same type. (camel_address_copy): New helper function to copy an address. * camel-mime-message.h (struct _CamelMimeMessage): Removed cached copy of date string. (struct _CamelMimeMessage): Added date_received info. * camel-mime-message.c (camel_mime_message_get_date_string): Removed. Nothing uses it anyway, and it is redundant. (camel_mime_message_finalize): No more date_str. (camel_mime_message_init): No more date_str, initialise date_received* (write_to_stream): Change the check for a date header. (process_header): No longer track the date_str. (camel_mime_message_get_received_date): Removed. totally invalid anyway. (camel_mime_message_get_sent_date): Removed. Redundant. The only 'date' is the sent date, the received date is just made up. (camel_mime_message_get_date): Args changed to be more consistent with utility functions. (camel_mime_message_get_date): Dont set the date when we're asked for it (if its not set by the time its written, it'll be set then). (camel_mime_message_get_date_received): Actually do 'the right thing' here, if we have a received header, use that to determine the received date. And return the data in the same format as get_date. (camel_mime_message_set_from): Changed the api to better match what we should be doing. Pass a camelinternetaddress, etc. (camel_mime_message_set_reply_to): Cahnged similarly to take an internetaddress. (camel_mime_message_get_reply_to): Likewise. (camel_mime_message_finalize): Unref the from/reply_to objects. (format_address): Removed, no longer needed. (process_header): Changed to store the from/reply_to as internetaddress's. (write_to_stream): Set the from header directly to empty, if we dont have one. Maybe we should just abort, and/or create one based on the current user. * camel-mime-utils.c (header_address_list_format): Renamed to header_address_list_encode, which is what it is actually doing. (header_address_list_format_append): Similarly. (encoding_map[]): Removed, no longer used. (header_address_list_encode_append): Take another arg, do we encode the address (for internet), or not (for display - utf8 only). (header_address_list_format): Re-added this function, but now it generates a display version only. Surprise surprise, that is all anythign needs to generate anyway. Sigh. * camel-internet-address.c (camel_internet_address_get): Return false if we get an invalid index only. (camel_internet_address_encode_address): Helper function to encode a single address for mailing. (internet_encode): Use the above function to format it. (camel_internet_address_format_address): Format a single address for display. (internet_format): Implement the display version. (camel_internet_address_class_init): Init the internet_format virtual function. (internet_cat): Implement virtual function to concatenate addresses. * camel-folder-summary.c (camel_folder_summary_info_new_from_header): new function, only build the summary info, dont add it. (camel_folder_summary_info_new_from_parser): Likewise, for new info from parser. (camel_folder_summary_add_from_parser): Cahnged to call function above to build info. (camel_folder_summary_add_from_header): Changed to call function above, to build info. (camel_folder_summary_info_free): New function to free the summary message info. (camel_folder_summary_clear): Changed to clal above to free info. (camel_folder_summary_remove): Likewise. (camel_folder_summary_add): Cleaned up the clashing uid re-assignment logic a little bit. (camel_folder_summary_decode_uint32): Fixed a typo, 01 != -1. (camel_folder_summary_decode_time_t): Return -1 on error. (camel_folder_summary_encode_off_t): New function to encode an off_t type. (camel_folder_summary_decode_off_t): And likewise for the reverse. (CAMEL_FOLDER_SUMMARY_VERSION): Bumped the summary version, since we're now encoding time/off_t's right. (summary_header_save): Use time_t encoder to save the timestamp. (summary_header_load): Likewise for decoding the timestamp. (content_info_load): Decode off_t types directly, now we can. (content_info_save): And likewise for encoding. (camel_folder_summary_add_from_message): New function, create a summary item from an existing message and add it. (camel_folder_summary_info_new_from_message): New function, create a summary item from an existing message. (summary_build_content_info_message): New function to do the dirty work of building the conent info/indexing, from a message source. (format_recipients): Format an internetaddress suitable for the summary. (message_info_new_from_message): Build a new summary item from a mime message. (content_info_new_from_message): Build a new conent info from a mime part. (camel_folder_summary_class_init): Init the new class functions. (message_info_new_from_message): Fixed for message api change. Added documentation to the functions. svn path=/trunk/; revision=6474
Diffstat (limited to 'camel/camel-charset-map.c')
-rw-r--r--camel/camel-charset-map.c73
1 files changed, 45 insertions, 28 deletions
diff --git a/camel/camel-charset-map.c b/camel/camel-charset-map.c
index c0b697290b..fd18337aae 100644
--- a/camel/camel-charset-map.c
+++ b/camel/camel-charset-map.c
@@ -204,36 +204,22 @@ void main(void)
#include <unicode.h>
#include <glib.h>
-unsigned int
-camel_charset_mask(unsigned int c)
+void camel_charset_init(CamelCharset *c)
{
- if (c>0xffff)
- return 0;
-
- return charset_mask(c);
+ c->mask = ~0;
+ c->level = 0;
}
-/* gets the best charset from the mask of chars in it */
-const char *
-camel_charset_best_mask(unsigned int mask)
+void
+camel_charset_step(CamelCharset *c, const char *in, int len)
{
- int i;
-
- for (i=0;i<sizeof(camel_charinfo)/sizeof(camel_charinfo[0]);i++) {
- if (camel_charinfo[i].bit & mask)
- return camel_charinfo[i].name;
- }
- return "UTF-8";
-}
-
-/* finds the minimum charset for this string NULL means US-ASCII */
-const char *
-camel_charset_best(const char *in, int len)
-{
- unsigned int mask = ~0;
- int level = 0;
+ register unsigned int mask;
+ register int level;
const char *inptr = in, *inend = in+len;
+ mask = c->mask;
+ level = c->level;
+
/* check what charset a given string will fit in */
while (inptr < inend) {
unicode_char_t c;
@@ -245,7 +231,7 @@ camel_charset_best(const char *in, int len)
}
inptr = newinptr;
if (c<=0xffff) {
- mask |= camel_charset_mask(c);
+ mask |= charset_mask(c);
if (c>=128 && c<256)
level = MAX(level, 1);
@@ -257,12 +243,43 @@ camel_charset_best(const char *in, int len)
}
}
- if (level == 1)
+ c->mask = mask;
+ c->level = level;
+}
+
+/* gets the best charset from the mask of chars in it */
+static const char *
+camel_charset_best_mask(unsigned int mask)
+{
+ int i;
+
+ for (i=0;i<sizeof(camel_charinfo)/sizeof(camel_charinfo[0]);i++) {
+ if (camel_charinfo[i].bit & mask)
+ return camel_charinfo[i].name;
+ }
+ return "UTF-8";
+}
+
+const char *camel_charset_best_name(CamelCharset *charset)
+{
+ if (charset->level == 1)
return "ISO-8859-1";
- else if (level == 2)
- return camel_charset_best_mask(mask);
+ else if (charset->level == 2)
+ return camel_charset_best_mask(charset->mask);
else
return NULL;
+
+}
+
+/* finds the minimum charset for this string NULL means US-ASCII */
+const char *
+camel_charset_best(const char *in, int len)
+{
+ CamelCharset charset;
+
+ camel_charset_init(&charset);
+ camel_charset_step(&charset, in, len);
+ return camel_charset_best_name(&charset);
}